SC-HVPPNet: Spatial and Channel Hybrid-Attention Video Post-Processing Network with CNN and Transformer

Guardat en:
Dades bibliogràfiques
Publicat a:arXiv.org (Apr 23, 2024), p. n/a
Autor principal: Zhang, Tong
Altres autors: Cui, Wenxue, Liu, Shaohui, Jiang, Feng
Publicat:
Cornell University Library, arXiv.org
Matèries:
Accés en línia:Citation/Abstract
Full text outside of ProQuest
Etiquetes: Afegir etiqueta
Sense etiquetes, Sigues el primer a etiquetar aquest registre!

MARC

LEADER 00000nab a2200000uu 4500
001 3044850056
003 UK-CbPIL
022 |a 2331-8422 
035 |a 3044850056 
045 0 |b d20240423 
100 1 |a Zhang, Tong 
245 1 |a SC-HVPPNet: Spatial and Channel Hybrid-Attention Video Post-Processing Network with CNN and Transformer 
260 |b Cornell University Library, arXiv.org  |c Apr 23, 2024 
513 |a Working Paper 
520 3 |a Convolutional Neural Network (CNN) and Transformer have attracted much attention recently for video post-processing (VPP). However, the interaction between CNN and Transformer in existing VPP methods is not fully explored, leading to inefficient communication between the local and global extracted features. In this paper, we explore the interaction between CNN and Transformer in the task of VPP, and propose a novel Spatial and Channel Hybrid-Attention Video Post-Processing Network (SC-HVPPNet), which can cooperatively exploit the image priors in both spatial and channel domains. Specifically, in the spatial domain, a novel spatial attention fusion module is designed, in which two attention weights are generated to fuse the local and global representations collaboratively. In the channel domain, a novel channel attention fusion module is developed, which can blend the deep representations at the channel dimension dynamically. Extensive experiments show that SC-HVPPNet notably boosts video restoration quality, with average bitrate savings of 5.29%, 12.42%, and 13.09% for Y, U, and V components in the VTM-11.0-NNVC RA configuration. 
653 |a Scandium 
653 |a Video post-production 
653 |a Modules 
653 |a Artificial neural networks 
653 |a Transformers 
653 |a Representations 
700 1 |a Cui, Wenxue 
700 1 |a Liu, Shaohui 
700 1 |a Jiang, Feng 
773 0 |t arXiv.org  |g (Apr 23, 2024), p. n/a 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3044850056/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full text outside of ProQuest  |u http://arxiv.org/abs/2404.14709